promptscan
REMOTEnicks-brn/promptscanProduction-ready prompt injection detection for AI agents. Scan user input, retrieved docs, and tool outputs before passing them to an LLM. Returns injection_detected, score, attack_type, and sanitized text.
○ Remote (HTTP) Server
This server runs on the internet and communicates over HTTP. It does not have direct access to your local filesystem or environment variables.
Uptime
100%based on 14 checks
← older · newer →
Security Scan
Security scan pending — this server has not yet been analyzed.
Risk Surface
Risk surface analysis pending — tool annotation scanning is coming soon.
Publisher Verification
Not yet verified by the Official MCP Registry.
Endpoint
https://promptscan--nicks-brn.run.toolsTools (1)
scan_text
Scan text for prompt injection attacks before passing it to an LLM. Returns injection_detected (bool), score (0.0–1.0), label, attack_type, layer_triggered, and latency_ms. If injection_detected is true, do NOT forward the text to your LLM.
Is this your server?
Create a free RNWY account to connect your on-chain identity to this server. MCP server claiming is coming — register now and you'll be first in line.
Create your account →